Technology Partners

Our Team

Our Awards

A team of people smiling and holding up their hands while holding paintbrushes

Social impact hero

Social Impact

Newsroom

World Map

Locations

Careers

About Us

Contact

Do Not Sell my Personal Information

Cookie Preferences

Culture Value Chain

iLabs Center for Innovation

Industries

Insights

Investor Relations

TELUS International is a subsidiary of: 

Privacy Shield Framework

Customer Privacy Policy

Solutions

Subscribe to Newsletter

Website User Terms

logo-x

Icon facebook

Icon youtube

Icon linkedin

Technology

Financial Services & Fintech

Automotive

Healthcare

Communications & Media

Games

Retail & Ecommerce

Travel & Hospitality

hero bulgaria locations

Bulgaria

A man in a brightly lit room smiling while on his phone

hero guatemala locations

Guatemala

Hero Morocco Locations

Morocco

hero romania locations

Romania

An aerial view of Cape Town, South Africa.

Hero South Africa Locations

South Africa

hero india locations

India

hero china locations

China

hero us locations

United States

Spain-Hero

Spain

hero philippines locations

Philippines

hero ireland locations

Ireland

Cityscape with Galata Tower and Gulf of the Golden Horn in Istanbul, Turkey.

Hero Türkiye Locations

Türkiye

hero el salvador locations

El Salvador

germany-hero

Germany

Europe-Hero

Additional European Centers of Excellence

infobrief

Guide

Resource Type Article

Article

case-studies thumb

Case Study

Preventing fraud for a global tech company in the travel and hospitality space image with fern in background

TI resource case 900x510

Video

whitepapers thumb

Research & Reports

checklists thumb

Checklist

brochures thumb

Brochure

ebooks thumb

E-book

Podcast Type Image

Podcast

The recent proliferation of generative AI (GenAI) models has sparked a lot of interest and excitement. These advanced large language models (LLMs) can do many extraordinary things — from crafting email responses to recommending a fitness routine to generating computer code; the list is seemingly endless.

However, these models aren't infallible. In fact, their propensity to sometimes hallucinate — a phenomenon where they provide responses that incorporate fabricated data that appears authentic — could significantly impact user trust. A recent TELUS International survey found that 61% of respondents were concerned about generative AI increasing the spread of inaccurate information online. 

Understanding what hallucinations are, why they happen and how to prevent them is critical to maintain users' trust in GenAI applications.

Introduction to generative AI hallucinations

A hallucination describes a model output that is either nonsensical or outright false. An example is asking a generative AI application for five examples of bicycle models that will fit in the back of your specific make of sport utility vehicle. If only three models exist, the GenAI application may still provide five — two of which are entirely fabricated. While this is a relatively low-stakes example of a hallucination, some could have far greater consequences. 

Recently a New York attorney representing a client's injury claim relied on a conversational chatbot to conduct his legal research. The federal judge overseeing the suit noted that six of the precedents quoted in his brief were bogus. It turns out that not only did the chatbot make them up, it even stipulated they were available in major legal databases.

While guardrails to prevent GenAI hallucinations need to be put in place, the first step is understanding how, or rather why, these inaccuracies happen.

Why do generative AI hallucinations occur?

While leading AI experts aren't entirely sure what causes hallucinations, there are several factors that are often cited as triggers.

First, hallucinations can occur if the training data used to develop the model is insufficient or includes large gaps leading to edge cases that are unfamiliar to the model. For example, in drafting a contract, a generative model that was fine-tuned using contracts from the financial services industry may not have sufficient exposure to terms and concepts in healthcare law to draft contracts for that industry. Most of the time, generative AI's primary goal is to produce an output in response to a prompt. Even if it doesn't "understand" the prompt, it might craft a response based on insufficient training data, thereby leading to a faulty result.

Similarly, some machine learning (ML) models suffer from overfitting, where the output is accurate for its training data, but inaccurate for new data. The goal of ML model training is to generalize from training instances so that the model can correctly operate on instances it hasn't seen before. Overfitting occurs when a model is trained to the point where it effectively memorizes the inputs and appropriate outputs for the training set, leaving it unable to generalize effectively to new data. For example, a model used to approve loan applications may be considered to be 90% accurate in predicting the likelihood of loan default. However, if it has been subject to overfitting, it likely has an accuracy rate closer to 70%. Therefore, applying the model to future loan decisions will result in a decrease in business profits and an increase in dissatisfied customers.

Another model development challenge is ensuring training texts and prompts are properly encoded. LLMs map terms to a set of numbers — a process known as a vector encoding — and these encodings have some key advantages over working with words directly. For example, words with multiple meanings can have one encoding per meaning, reducing the chance of ambiguity. So, the word "bank" would use one vector representation when referring to a financial institution and another when referring to the shore of a river. Vector representations also allow mapping semantic operations — like finding a similar word — into mathematical operations. Problems with encoding and decoding between text and representations can lead to hallucinations.

Best practices to prevent generative AI hallucinations

While generative AI hallucinations are a concerning issue, there are ways to reduce their frequency and intensity. Consider the following best practices.

The most obvious protection from hallucinations is high-quality input data. It's critical that your GenAI model is trained on a diverse and representative dataset that covers a wide range of real-world examples. Using sufficient, unbiased data is key to training an accurate, resilient model.

Another crucial part of the training process is incorporating human feedback, also known as reinforcement learning from human feedback (RLHF). Because AI models lack a nuanced understanding of language, they can produce responses that are out of context or irrelevant. RLHF provides models with regular corrections via feedback from people, so that an understanding of the world that only a human can have is incorporated into the training process.

Transparency in AI ensures that it's possible to understand a model's inner workings and how it makes decisions. The issue is coming to the forefront as LLMs evolve, particularly because more advanced models are harder to understand.

Users and machine learning professionals should be able to evaluate how a model was trained and review for potential weaknesses in the learning process. Transparency also makes it easier to identify and correct errors that can lead to hallucinations.

A malicious user of a generative AI system could experiment and probe a model looking for ways to make it hallucinate. It's necessary to incorporate counter measures to help monitor and control the types of inputs allowed in generative AI systems. These include using adversarial examples in the model's training to improve its ability to respond appropriately and to audit the model's anomaly detection capabilities. A further means is by data sanitization, which involves checking that no malicious inputs are being fed into the model. And finally, security updates and patches can help block external threats to your AI model.

While generative AI hallucinations are a frustrating hurdle that can significantly impact user trust, they aren't insurmountable. By training models using high-quality data, ensuring model transparency and enacting effective quality control, developers can improve their model's resiliency to deliver accurate predictions.

Hallucinations are an obstacle to building user trust in generative AI applications. Learn about the phenomenon, including best practices for prevention.

Single line drawing of the side profile of a head and the term "AI" imposed on a wavy background connoting hallucination

ai hallucination

Check out our solutions

Generative AI

Generative AI hallucinations: Why they occur and how to prevent them

6-steps-for-Conversational-Bot-success-A-primer 

Make the most of your conversational bot investment with our easy-to-follow guide featuring best practices that can be applied to your digital transformation journey.

A conversational bot floating above a mobile phone

(Hero) 6-steps-for-Conversational-Bot-success-A-primer hero

An illustration of a bot floating above a mobile phone

(Featured) 6-steps-for-Conversational-Bot-success-A-primer

Six steps for conversational bot success: A helpful primer for chatbot implementation

IDC Info Snapshot - Content Moderation thumbnail

In this IDC Info Snapshot, discover the benefits of engaging an experienced CX partner for content moderation to safeguard your online communities.

IDC Info Snapshot - content moderation hero

IDC Info Snapshot - content moderation feature image

Expanding content moderation capabilities helps fast-growing brands earn customer trust 

A survey conducted by TELUS International unveiled consumer concerns about misinformation and bias in generative AI. Learn more.

Illustration of friendly robots and smart phones displaying iconography of humans, arrows and support agents, all meant to symbolize generative AI transparency and trust.

genai trust

Generative AI survey results: Customers expect brands to be transparent

A copy of the Digital customer experience priorities in 2023 report on top of a green leafy plant.

Digital Customer Experience Priorities 2023 Preview Image

TELUS International, in partnership with Statista, surveyed 250 enterprise leaders to explore where they plan to invest in digital customer experience (CX) technology in 2023. Uncover the results.

An illustrated representation of customer profiles and leaving a five-star review online.

Digital Customer Experience Priorities 2023 Hero

Survey results: Digital customer experience priorities for leaders in 2023

A copy of the outsourcing locations e-book on a white tablet on top of a green fern.

Outsourcing Locations E-book Feature

Discover some of the top outsourcing destinations for consideration and the factors to keep in mind as you make your decision.

Feature-Landing-Image Locations Outsourcing

Selecting the best outsourcing destination for your business

Are you familiar with multimodal voice? Learn more about the technology set to have an important role in the future of digital CX. 

Illustration of two people standing in front of a smartphone with a speaker icon meant to symbolize voice assistance.

multimodal voice

Now we're talking: Multimodal voice and the future of digital CX

Deploying automation to assist agents at a consumer robotics company image with fern in background

Preview image: Deploying automation to assist agents at a consumer robotics company

Want to speak with an expert?

Help your agents reach their full potential with automation

Even consumer robotics companies can benefit from a little help deploying customer experience (CX) automation. Learn more about TELUS International’s solution to improve a client’s agent efficiency and engagement.

Learn about how we helped a consumer robotics company improve their digital customer experience with agent-facing automation.

PDF for case study titled "Deploying automation to assist agents at a consumer robotics company"

Deploying automation to assist agents at a consumer robotics company

Illustration of consumer robotics including a butler, a chef and cat riding a robot vacuum.

AI Bots

In this virtual chat with TELUS International computer vision experts Ajinkya Malasane and Kaushik PS, we’ll dive deep into end-to-end sensor fusion data collection and annotation solutions for autonomous vehicle training needs.

Three cars on road with labeling boxes around them

3d data annotation

Leveraging automation for labeling large 3D pipelines

The cover of The future of content moderation: Strategies and tools for 2023 and beyond e-book with a fern in the background.

The future of content moderation: Strategies and tools for 2023 and beyond

Organizations have a responsibility to create and maintain digital experiences that are truthful, welcoming and safe. Learn how brands can keep pace with the growing levels of user-generated content (UGC) to build trust with their customers and protect their reputation.

An illustration of various people creating user generated content on their phones.

Games fraud is on the rise as the gaming industry continues to experience significant growth. Discover best practices for combatting games fraud while improving the player experience.

PX games fraud

Improving the player experience by combatting games fraud​​

Preview image of the Forrester report "How To Set CX Metrics Goals" and a plant

TI Resource ForresterReport

Gain an understanding of the challenges faced by customer experience (CX) leaders in setting goals for their metrics — and effective techniques to persevere.

Illustration of a person and various graphs and scales symbolizing metrics, measurement and KPIs

Hero image for Forrester - How to set CX metrics goals - 1620x550

Forrester - How to set CX metrics goals - card image

How to set CX metrics goals

Preview image of the report "CX outsourcing in 2023" accompanied by a plant

TI Resource WhitePaper 2023

Delve into new insights about customer experience outsourcing from a survey of 712 enterprise executives with strategic decision-making authority.

Illustration of customer support agents surrounded by related iconography like charts, star ratings and text boxes.

CX Outsourcing2023 Hero Image

Cover image for the dynamic report "CX outsourcing in 2023" featuring the title and illustrations of customer support agents and related iconography 

CX Outsourcing in 2023

Executive survey results: CX outsourcing in 2023

TI resource eBook 800x450 The essential guide to training data 

Discover best practices for the sourcing, labeling and analyzing of training data from TELUS International, a leading provider of AI data solutions.

guide to AI training data - website hero image 

The essential guide to AI training data

Join experts from TELUS International and Automation Anywhere, a top cloud automation platform, to learn how banks and financial services firms can leverage automation to enhance the customer experience, optimize operations and foster customer loyalty.

An illustration showing various digital automation technologies for banking including, artificial intelligence, mobile payments, chatbots and data analytics.

The future of banking and financial services webinar

The future of banking and financial services: Unlocking customer experience potential with intelligent automation

Germany's diverse and talented workforce make the European nation an ideal CX outsourcing destination. Read up on all the benefits.

Photograph of the 'Reichstag' in Berlin, Germany

germany

Don't overlook Germany as a CX outsourcing destination

Preview TI resource case SecurityForOnlineGames

TI resource case SecurityForOnlineGames 900x510

Uncover how TELUS International supported a games client by replicating their culture within support centers, while also addressing perceived risks related to site security, IT vulnerability and information safeguarding.

Security for Online Games Company - Case Study

Fraud Prevention & Detection

Protecting the games - physical, IT and information security

To borrow famous words from 1986's The Legend of Zelda, "It's dangerous to go alone!"

Protecting the games - physical, IT and information security

Share